CN108961747A - A kind of urban road traffic state information extracting method under incomplete bayonet data qualification - Google Patents
A kind of urban road traffic state information extracting method under incomplete bayonet data qualification Download PDFInfo
- Publication number
- CN108961747A CN108961747A CN201810714830.9A CN201810714830A CN108961747A CN 108961747 A CN108961747 A CN 108961747A CN 201810714830 A CN201810714830 A CN 201810714830A CN 108961747 A CN108961747 A CN 108961747A
- Authority
- CN
- China
- Prior art keywords
- data
- section
- time
- period
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
Abstract
This patent discloses a kind of urban road traffic state information extracting methods under incomplete bayonet data qualification, specifically include following steps: step 1, the pretreatment of incomplete data；Step 2, completion missing data；Step 3, extract road traffic state information, the present invention is suitable for the extraction to urban road traffic state information, based on incomplete bayonet data, loss tracing point is found out using the depth-first traversal of optimization, then the temporal information for losing tracing point is found out using Lagrangian type polynomial interpolation, and then road traffic state information can be extracted.
Description
Technical field
The present invention relates to urban traffic status information under traffic information field more particularly to incomplete bayonet data qualification to mention
Take method.
Background technique
With the raising of the overall national strength and living standards of the people in China, the quantity of motor vehicle is every year with 10%~20%
Speed increases, and in order to reinforce building to the supervision of motor vehicle and urban roadization, tollgate devices are laid quantity and also obtained substantially
It is promoted.Road gate monitoring system can be monitored bayonet with round-the-clock, and remember to all types of vehicular traffics
Record, and abundant information is recorded, it is numbered comprising bayonet, license plate number, crosses the information such as vehicle time.It can be to city using bayonet data
City's road traffic state information is extracted and is analyzed, but since bayonet Monitor Equipment technical level and bayonet monitor
The limitation of implantation of device bayonet number etc., inevitably will appear record information lose and record point missing etc. information record it is incomplete
Phenomenon causes the urban traffic status information extraction under incomplete bayonet data qualification difficult.So needing to study incomplete card
Urban road traffic state information extracting method under mouth data qualification.
Currently, the research about road traffic state information extraction have very much, application No. is 201510938922.1 it is special
A kind of benefit --- " traffic circulation state characteristic parameter extraction method based on big data " is based on GPS data and mobile phone signaling number
It is extracted according to car speed and vehicle flow parameter, method is not suitable for bayonet data.There are also a large amount of in the prior art
Based on the technical solution that bayonet data extract traffic information, but it is incomplete for bayonet data in the case where it is common
Way is by the rejection of data, such as application No. is 201510225291.9 patents --- " vehicle number is crossed based on extensive bayonet
According to the real-time passage speed calculation method of road " although being the extracting method based on bayonet data to link speed information, it is right
In the bayonet data for having missing and it is not suitable for.
Summary of the invention
Traffic state information extracting method that the invention proposes one kind in the case where the bayonet loss of data of part, by right
Effective bayonet information is supplemented, and the location information for recording it, temporal information and information of vehicles are relatively complete, completion pair
The extraction of urban road traffic state information.
In order to solve the above-mentioned technical problem, the technical solution of this patent offer includes:
A kind of urban road traffic state information extracting method under incomplete bayonet data qualification, the method packet are provided
Include following steps: step 1, the pretreatment of incomplete data
1.1 vehicle travels divide
The pretreatment of data includes recording the bayonet data put, and rejecting abnormalities from all in selection road network in database
Data and repeated data；This partial data is classified according to license plate number, and distributes and numbers to each car；It is right in chronological order
The data of each car are arranged；Finally, dividing to vehicle travel, division methods are as follows:
(1) section transit time set T is arranged by required average time according to section each in road network normally travel
={ T1, T2..., TV, the maximum of T in setu(u ∈ V) is used as threshold value.
(2) in above-mentioned data according to time sequence, if every two adjacent data time differences of each car are greater than threshold value,
Then think that vehicle has stop between the two record points, needs data from the separated of the two record points, so by this
Two records put the former and its pervious data and are considered as stroke A, and the latter and its later record point are considered as stroke B.Such as Fig. 2 institute
Show, certain vehicle by bayonet number be between 187 and 024 bayonet the consumed time be greater than threshold value, then it is assumed that this vehicle
There is stop between two bayonets, therefore its driving trace is disconnected from there, is divided into stroke A and stroke B.If but in stroke B
The case where still having the adjacent data time difference to be greater than threshold value, can then continue stroke division to stroke B.
(3) stroke of only one record is rejected, and to remaining stroke distribution number to record stroke dividing condition.
1.2 calculating section evaluation indexes
Each link flow of primary Calculation and speed, two evaluation indexes needed for calculating as subsequent entropy assessment are specific to count
Calculation method is as follows:
(1) one day time was divided into n period using t as the period (t can use 5min, 10min etc.), to each period
Data are traversed, and bayonet number k, the license plate number m of pieces of data are extracted, and cross the information such as vehicle time s, calculate each week time
By the vehicle number of all directions of each bayonet in phase, the flow information q in you can get it each section each perioddj, wherein d is section
Number, j are j-th of time cycle.
(2) section speed v still is calculated by the period of tdj, bayonet number k, the license plate number m of data are read by stroke, cross vehicle
The information such as time s calculate the time difference per adjacent two data: Δ s=si+1-si, then with corresponding road section length divided by the time
Difference can obtain speed, and calculation formula is as follows:
Wherein vdiBy the bayonet number k of the i-th data with the bayonet number k+1 of the i+1 data section d's connected
One velocity amplitude, Δ s are the difference of the time of i+1 data and the time of i data, ddFor the length of section d.
The speed average in its each section i.e. section speed in the period thus is asked to the data in each period, formula is such as
Under:
Wherein, vdjFor the speed average of the section d in j-th of time cycle, ∑ vdjFor the road of j-th of time cycle
All velocity amplitude v of section ddiSum, h is v in j-th time cyclediNumber.By section number d, period j, section is flat
Equal speed vdjIt is stored in database, each section can be obtained in the speed of each period.
(3) since original bayonet data have missing, therefore the flow in required section and speed are imperfect.If the stream in certain section
Amount or speed in certain period have missing, the flow or speed approximate substitution of this section adjacent time interval may be used.
Step 2, completion missing data
If if location information shown by the data of certain stroke can be successively present in each adjacent bayonet of road network, i.e.,
Breakpoint is not present in its trace information, then this trip data can be used directly without missing to extract road traffic state information.Such as figure
Stroke A shown in 2, run-length data is without missing；If location information shown by the data of certain stroke cannot sequentially connect in road network
Knot, i.e., there are breakpoints for its trace information, then this trip data have missing, after needing to supplement completely the data of each of which breakpoint
It can be used.Stroke B as shown in Figure 2 numbers shortage of data at the bayonet for being 026, rail shown by run-length data in bayonet
Mark position is 028 to 186.The data for traversing each stroke extract its location information, and judge that its track with the presence or absence of breakpoint, mentions
The run-length data there are shortage of data is taken to be supplemented.
2.1 calculate the position of missing point
The depth-first traversal of optimization need to be used to calculate the track of its lack part for there are the data of missing, it is specific to walk
It is rapid as follows:
(1) all possible roads of the corresponding beginning and end in shortage of data part are found out using the method for depth-first traversal
Diameter, and all possible paths are screened for the first time, the bayonet number phase finding out wherein shortest path and being passed through with shortest path
Difference is less than or equal to 3 all paths, if the collection of the possible path of certain stroke lack part is combined into R={ r1, r2..., rn, wherein
riIndicate the i-th paths in the set in path.Wherein n is the sum of qualified possible path.
(2) path length is selected, path average speed, section quantity, path average flow rate is as evaluation index.Path length
The length in each section that degree is passed through for every possible path be L={ l with set expression1, l2..., ln}T, wherein li(i∈
N) length and i.e. l in each section that i-th possible path is passed through are indicatedi=∑ dd；Path average speed can energy circuit for every
The speed average of each section that diameter is passed through during that corresponding time period, is V={ v with set expression1, v2..., vn}T, wherein vi
(i ∈ n) indicates the average speed v in each section that i-th possible path is passed throughdjAverage value, i.e., Section quantity is
The quantity in the section that every possible path is passed through is C={ c with set expression1, c2..., cn}T, wherein ci(i ∈ n) indicates the
The quantity in the section that i possible path is passed through；Each section that path average flow rate is passed through by every possible path is in correspondence
Flow average value in period is Q={ q with set expression1, q2..., qn}T, wherein qi(i ∈ n) expression i-th can energy circuit
The flow q in each section that diameter is passed throughdjAverage value, i.e.,It is carried out really with weight of the entropy assessment to each evaluation index
It is fixed, initial matrix is obtained first:
(3) road average-speed and link flow are high excellent index, road section length and section in aforementioned four evaluation index
Quantity is low excellent index, should have same tendency between different indexs, therefore counting backward technique is used to convert Gao You for low excellent index
Index, the matrix after conversion are as follows:
(4) Y matrix is normalized, i.e., with the element yi of each column vector in Y matrixjWith all members of the vector
The corresponding element for the matrix Z that the ratio of the sum of element is obtained as normalization, the matrix after normalization are as follows:
(5) the entropy weight H (x of each evaluation index is determinedj), (j=1,2,3,4), specific formula are as follows:
Wherein k is adjustment factor,zijFor the standardized value of j-th of evaluation index of i-th of evaluation unit, i.e. Z square
I-th row in battle array, the element of jth column.
(6) weighted value is converted by the entropy of evaluation index, the weight of each evaluation index, specific formula can be obtained
Are as follows:
Wherein, djFor the weight of the evaluation index of jth column, and 0≤dj≤ 1,M is the number of evaluation index,
That is m=4.
(7) weight of each index is distinguished corresponding index mark by the entropy weight comprehensive evaluation value for determining each evaluation index
Quasi-ization value is summed after being multiplied, formula are as follows:
Wherein, UiFor the entropy weight comprehensive evaluation value of i-th possible path；The maximum path of entropy weight comprehensive evaluation value is chosen to make
For the track of shortage of data part.
2.2 calculate the time of missing point
Using the temporal information of shortage of data partial traces point at Lagrangian type polynomial interpolation calculating, then
Obtain link flow, section speed, road-section average vehicle density, the specific steps of which are as follows:
(1) the previous bayonet record for setting track data lack part is put as O point, the latter of track data lack part
Bayonet record point is D point, and enabling the previous bayonet of O point record point if having data before O point is A point, if no data before O point
Then A point etc. and O point.The distance for enabling O point to A point is x0, the distance of D point to A point is x1, each tracing point of shortage of data part to A
The collection of the distance of point is combined into X={ x1,x2,…,xd, wherein xuThe distance of A point is arrived for u-th point.By the time point of O point and D point
It is converted into timestamp, and is denoted as y respectively0, y1。
(2) time value that each shortage of data partial traces point is calculated using Lagrangian type interpolation polynomial, can be obtained
Set P={ the p of the time value of each tracing point1,p2,…,pd, wherein puFor u-th point of time value, Lagrangian type interpolation
The specific formula of multinomial are as follows:
Wherein 1≤u≤d, and xu∈X。
(3) time format in initial data is converted by the time value in set P, and by the bayonet of corresponding tracing point
Number, license plate number, the excessively information such as vehicle time are added in this vehicle travel data can be complete by this trip information supplement.It will mend
Charge it is whole after data and without missing Data Integration, to use in next step.
Step 3 extracts road traffic state information
(1) one day time was divided into n period using t as the time cycle (t can use 5min, 10min etc.), to each week
The data of phase are traversed, and bayonet number k, the license plate number m of pieces of data are extracted, and the information such as vehicle time s are crossed, when calculating each
Between in the period by the vehicle number of all directions of each bayonet, the flow q in you can get it each section each perioddj, wherein d is section
Number, j are j-th of time cycle.By section number d, period j, link flow qdjIt is stored in database, each section can be obtained
In the flow of each period.
(2) section speed v still is calculated by the period of tdj, bayonet number k, the license plate number m of data are read by stroke, cross vehicle
The information such as time s calculate the time difference per adjacent two data: Δ s=si+1-si, then with corresponding road section length divided by the time
Difference can obtain speed, and calculation formula is as follows:
Wherein vdiBy the bayonet number k of the i-th data with the bayonet number k+1 of the i+1 data section d's connected
One velocity amplitude, Δ s are the difference of the time of i+1 data and the time of i data, ddFor the length of section d.
The speed average in its each section i.e. section speed in the period thus is asked to the data in each period, formula is such as
Under:
Wherein, vdjFor the speed average of the section d in j-th of time cycle, ∑ vdjFor the road of j-th of time cycle
All velocity amplitude v of section ddiSum, h is v in j-th time cyclediNumber.By section number d, period j, section is flat
Equal speed vdjIt is stored in database, each section can be obtained in the speed of each period.
(3) road-section average density is calculated by the period of t, successively using the link flow in each period divided by corresponding section
The road-section average density in this period, calculation formula can be obtained in average speed are as follows:By section number d, period j, road
Duan Midu kdjIt is stored in database, each section can be obtained in the density of each period.
The present invention is suitable for the extraction to urban road traffic state information, and based on incomplete bayonet data, use is excellent
The depth-first traversal of change finds out loss tracing point, is then found out using Lagrangian type polynomial interpolation and loses tracing point
Temporal information, and then road traffic state information can be extracted.
Detailed description of the invention
Fig. 1 is urban road traffic state information extraction flow chart proposed by the present invention；
Fig. 2 is that vehicle travel proposed by the present invention divides schematic diagram；
Fig. 3 is the bayonet position view in present example；
Fig. 4 is 13 section velocity profiles in present example.
Specific embodiment
Below in conjunction with attached drawing and example, the present invention is described in further detail.
Urban road traffic state information extracting method under incomplete bayonet data qualification proposed by the present invention, it is main to wrap
Include: link flow and speed are estimated in the pretreatment of data, extract the data that there is missing, are calculated missing tracing point position, are extracted
Five small steps of road traffic state information, process as shown in Figure 1, specifically:
Step 1, the pretreatment of missing data
1.1 vehicle travels divide
From the bayonet data for extracting all record points in road network in database according to bayonet number information, and rejecting is wherein
License plate number fails the abnormal datas such as the record of identification, then deletes bayonet number, and license plate number crosses vehicle time all identical number
According to；Data after rejecting abnormalities data and repeated data are arranged according to license plate number, and distribute a number to each car；
The data of each car are arranged in chronological order again, can be obtained all satisfactory and are arranged by car number and time
The data of column；Finally, being divided in accordance with the following steps to vehicle travel:
(1), section transit time set T is arranged by required average time according to section each in road network normally travel
={ T1, T2..., TV, wherein V need to be determined according to the quantity in section in road network, Tu(u ∈ V) is the average traveling in the u articles section
Time.Take the maximum value in setAs threshold value come to judging whether to need to divide vehicle travel.
(2), in the data for having pressed car number and time-sequencing, two adjacent datas of each car is successively chosen and are asked
Its time difference, if the time difference be greater than threshold value, then it is assumed that vehicle the two record point between have stop, need by data from this two
A record point it is separated so that it is divided into two strokes, so by the former and its pervious data of the two record points
It is considered as stroke A, the latter and its later record point are considered as stroke B.If but still thering is the adjacent data time difference to be greater than threshold value in stroke B
The case where, then it can continue stroke division to stroke B.
(3), the data divided through overtravel are likely to occur some stroke and there was only the case where record, need to be by such stroke
It rejects, and remaining stroke is distributed and is incremented by number to record stroke dividing condition.
It is " Anhui CXXXXX " that this example, which intercepts a license plate number, for temporal information is the vehicle registration of " 2017-06-01 "
Illustrate that the data format after vehicle travel divides, data include that information is as follows:
" Anhui CXXXXX " vehicle travel of table 1 divides table
| Bayonet number | License plate number | Spend the vehicle time | Trip number |
| 035 | Anhui CXXXXX | 2017-06-0111:28:15 | 1 |
| 533 | Anhui CXXXXX | 2017-06-0111:30:47 | 1 |
| 054 | Anhui CXXXXX | 2017-06-0120:34:54 | 2 |
| 026 | Anhui CXXXXX | 2017-06-0120:39:54 | 2 |
| 343 | Anhui CXXXXX | 2017-06-0121:35:20 | 3 |
| 024 | Anhui CXXXXX | 2017-06-0121:39:27 | 3 |
| 187 | Anhui CXXXXX | 2017-06-0121:42:10 | 3 |
Wherein 1 in trip number, 2,3 respectively indicate the first segment stroke of this vehicle, second segment stroke, third section row
Journey.Every section of stroke all contains number information and the information record time of bayonet monitoring device.
1.2 calculating section evaluation indexes
Because subsequent calculating need to use the flow and velocity information in section, therefore tentatively each link flow and speed are counted
It calculates, since bayonet data are imperfect, so the flow and velocity information that are calculated must have missing, lack part need to be done closely
Like processing.Circular is as follows:
(1), one day time was divided into 144 periods for the period with 10 minutes, by the temporal information in every data
For judgment basis, the data in each 10 minute period are traversed, extract bayonet number k, the license plate number m of every data,
The information such as vehicle time s are crossed, vehicle one bayonet of every process will generate one and cross vehicle record, therefore need to only count when calculating flow
The item number continuously across certain two adjacent bayonet data in each 10 minute period, section as where the two adjacent bayonets
Flow qdj.If certain vehicle passes through first bayonet in certain section, the time is recorded in previous 10 minute period, by second
When a bayonet, the time is recorded in next 10 minute period, the then flow being included into previous 10 minute period.According to this side
Method calculates, the flow information in you can get it each section each 10 minute period, finally by its section number d, period j, flow
qdjIt is stored in database, prepares for subsequent calculating.
(2), section speed still was calculated for the period with 10 minutes, bayonet number k, the license plate number m of data is read by stroke,
The information such as vehicle time s are crossed, the time difference Δ s per two adjacent datas is calculated and are stored in seconds, each stroke is most
The time difference of latter data is denoted as 0, then can be obtained with the length of adjacent two datas corresponding road section divided by its time difference corresponding
A velocity amplitude v in vehicle time in corresponding 10 minute period is crossed at it in sectiondi, then to 10 minute week of each of each section
The speed data of phase is averaged vdjSection speed as in 10 minute period.By velocity information vdjAccording to corresponding road section
In corresponding period j deposit database, prepare for subsequent calculating.
(3), since original bayonet data have missing, therefore the flow in required section and speed are imperfect.It is likely to occur certain
Data of the flow or speed in section within some 10 minute period have the case where missing, this section adjacent time interval may be used
Flow or speed approximate substitution.
The section that this example interception section number is 1 is that " 2017-06-0103:40:00 " arrives " 2017-06- in temporal information
The speed of 0104:10:00 ", to illustrate that the data format and its calculating process of section speed, data are as shown in the table:
2 section speedometer of table
| Section number | Section speed | Period starting point | When segment endpoint |
| 1 | 9.750 | 2017-06-0103:40:00 | 2017-06-0103:50:00 |
| 1 | 9.243 | 2017-06-0103:50:00 | 2017-06-0104:00:00 |
| 1 | 9.180 | 2017-06-0104:00:00 | 2017-06-0104:10:00 |
Wherein, section speed unit is " m/s ", and the up direction bayonet number in section 1 is 175, and down direction bayonet is compiled
Number be 442.When speed to calculate first period in this example, it need to first find out and all be successively continuously across bayonet number
175 and 442 and make temporal information in " 2017-06-0103:40:00 " and " 2017-06-0103:50:00 " by bayonet 175
Between data, with the length in section 1 divided by the time difference of each group of data, then be averaged, as section 1 is in " 2017-
06-0103:40:00 " arrives the average speed in " 2017-06-0103:50:00 " this 10 minute period.
Step 2, completion missing data
The data of each stroke are traversed, if bayonet number of certain stroke per two adjacent datas successively waits on Mr. Yus section
The bayonet of line direction and down direction number, then this trip information is complete, its bayonet position is shown according to the time sequencing of record
A complete track can be linked to be in map along road by showing.Such data can be directly used for road condition letter without missing information
The extraction of breath；If there are the bayonet of two adjacent datas numbers not equal to two bayonets that the same section is connected for certain stroke
Bayonet number, then there is missing in such data, the starting point bayonet number and terminal bayonet number of its lack part be extracted, for meter
The bayonet number information for calculating each tracing point of its lack part is prepared.
2.1, calculate the position of missing point
The depth-first traversal of optimization need to be used to calculate the track of its lack part for there are the data of missing, it is specific to walk
It is rapid as follows:
(1), it is known that the bayonet of beginning and end is numbered, its corresponding location information can be obtained, and is connected and is closed using road network
System finds out all possible paths of beginning and end using the method for depth-first traversal, and carries out to all possible paths first
Screening finds out wherein shortest path and differs all paths less than or equal to 3 with the bayonet number that shortest path is passed through, due to this
Example selected by city road network be checkering, therefore can simplify path screening process choose its by the least path of bayonet number and with
The bayonet number difference in the minimum path of bayonet number is less than or equal to 3 all paths.This example is with the shortage of data portion in stroke 3 in table 1
It is divided into the calculating that example illustrates its missing point position.Wherein bayonet number is that the data between 343 to 024 have missing, uses depth
First traversal and after being screened for the first time to its possible path the collection of its possible path is combined into R={ r1, r2..., rn, wherein ri
Indicate the i-th paths in the set in path.Wherein n is the sum of qualified possible path, and this example obtains four after screening
Possible path, therefore n=4.Wherein r1Indicate the 1st article of possible path, the number of passed through bayonet is successively are as follows: 343,344,345,
024；r2Indicate the 2nd article of possible path, the number of passed through bayonet is successively are as follows: 343,344,028,024；r3Indicate the 3rd article of possibility
Path, the number of passed through bayonet is successively are as follows: 343,026,028,024；r4Indicate the 4th article of possible path, passed through bayonet
Number is successively are as follows: and 343,023,186,026,028,024, it is as shown in Figure 3 that each bayonet numbers corresponding position.
(2), selection path length, path average speed, section quantity, path average flow rate judge as evaluation index
Track of the most Utopian section as lack part in above-mentioned possible path set, wherein path length can energy circuit for every
The length in each section that diameter is passed through and, be L={ l with set expression1, l2..., ln}T, this example is computed to obtain its path length
Collection be combined into L={ 2147,2169,1950,2725 }T；Each section that path average speed is passed through by every possible path exists
The average value of speed in the corresponding period, is V={ v with set expression1, v2..., vn}T.This example is computed each possible path
The collection of path average speed is combined into V=within the period of " 2017-06-0103:30:00 " to " 2017-06-0103:40:00 "
{ 7.095,6.044,5.786,6.104 }T；The quantity in the section that section quantity is passed through by every possible path, uses collection table
It is shown as C={ c1, c2..., cn}T, the possible path section magnitude-set that this example acquires is C={ 3,3,3,5 }T；Path mean flow
The flow average value of each section that amount is passed through by every possible path during that corresponding time period, is Q={ q with set expression1,
q2..., qn}T.This example is computed every possible path and arrives " 2017-06-0103:40:00 " at " 2017-06-0103:30:00 "
Period in path average flow rate collection be combined into Q={ 104,60,51,50 }T；It is carried out really with weight of the entropy assessment to each evaluation index
It is fixed, initial matrix is obtained first, and data are brought into:
(3), in path length, path average speed, section quantity, section is flat in four evaluation indexes of path average flow rate
Equal speed and link flow are high excellent index, i.e., are conducive to vehicle pass-through when its numerical value is higher.Road section length and section quantity are
Low excellent index, i.e., be conducive to vehicle pass-through when its numerical value is lower.There should be same tendency between different indexs, therefore use reciprocal
Low excellent index is converted high excellent index by method, i.e., seeks its inverse to low excellent index, and high excellent index value is constant, is written by corresponding position
Y matrix.Matrix after conversion are as follows:
(4), Y matrix is normalized, i.e., with the element y of each column vector in Y matrixijWith all members of the vector
Matrix of the ratio of the sum of element as normalizing the obtained corresponding element of matrix Z, after the normalization that this example is acquired by formula are as follows:
(5), the entropy weight H (x of each evaluation index is determinedj), (j=1,2,3,4), specific formula are as follows:
Wherein k is adjustment factor,zijFor the standardization of j-th of evaluation index of i-th of evaluation unit
Value, i.e. the i-th row in Z matrix, the element of jth column.Specific to this example, the corresponding element of the Z matrix acquired in (4) is brought into above-mentioned
Formula acquires:
H(x1)=0.3543, H (x2)=0.3554, H (x3)=0.3510, H (x4)=0.3530,
(6), weighted value d is converted by the entropy of evaluation indexj, (j=1,2,3,4) seeks the power of each evaluation index
Value, specific formula are as follows:
Wherein, djFor the weight of the evaluation index of jth column, and 0≤dj≤ 1,M is the number of evaluation index,
That is m=4.H (the x that will be acquired in (5) specific to this examplej), (j=1,2,3,4) brings above-mentioned formula into and can acquire:
d1=0.2487, d2=0.2482, d3=0.2510, d4=0.2530
(7), the weight of each index is distinguished corresponding index mark by the entropy weight comprehensive evaluation value for determining each evaluation index
Quasi-ization value is summed after being multiplied, formula are as follows:
Wherein, UiFor the entropy weight comprehensive evaluation value of i-th possible path；The maximum path of entropy weight comprehensive evaluation value is chosen to make
For the track of shortage of data part.Collective is to this example, by the d in (6)j, corresponding element in (j=1,2,3,4) and Z matrix
Above-mentioned formula is brought into obtain:
U1=0.3029, U2=0.2504, U3=0.2467, U4=0.2009
Due to evaluation function value U1Maximum, therefore select first possible path in possible path set as missing portion
There is the location information of each bayonet known to each bayonet number information in first possible path in the track divided.
2.2, calculate the time of missing point
After the location information for acquiring missing point, data are still imperfect, and needing to find out its temporal information just can be used.This example
Using the temporal information of shortage of data partial traces point at Lagrangian type polynomial interpolation calculating, section is asked to flow to be subsequent
Amount, section speed, road-section average vehicle density are prepared, the specific steps of which are as follows:
It (1), is the starting point of possible path in this example if the previous bayonet record point of track data lack part is O point
For O point, i.e., the bayonet that number is 343 is O point.The latter bayonet record point of track data lack part is D point, is in this example
The terminal of possible path is D point, i.e., the bayonet that number is 024 is D point.There is no data before this stroke O point, therefore A point is equal to O
Point.The distance for enabling O point to A point is x0, i.e. x0The distance of=0, D point to A point is x1, i.e. x1=2147m, shortage of data part
The collection of distance of each tracing point to A point is combined into J={ j1,j2,…,jd, wherein ju(u ∈ [1, d]) be u-th point to A point away from
From.The resulting J=of this example { 653,1182 }, distance of each bayonet to A point in respectively calculated path.By O point and D point
Time format is converted into the second, and is denoted as y respectively0, y1.The time point of O point and D point is converted timestamp by this example, obtains y0=
1496324120s, y1=1496324367s.
(2), the time value that each shortage of data partial traces point is calculated using Lagrangian type interpolation polynomial, can be obtained
Set P={ the p of the timestamp of each tracing point1,p2,…,pd, wherein puThe timestamp that (u ∈ [1, d]) is u-th point, glug
The bright specific formula of day type interpolation polynomial are as follows:
Wherein 1≤u≤d, and xu∈X.The obtained each numerical value of this example is brought by formula requirement:
P={ 1496324195,1496324255 }
(3), the time format in initial data is converted by the timestamp in set P, converted obtains: p1For 2017-
06-0121:36:35, p2For 2017-06-0121:37:35.And number the bayonet of corresponding tracing point, license plate number, cross vehicle
The information such as time are added in this vehicle travel data can be complete by this trip information supplement.This example has supplemented this trip data
After whole as shown in table 3.Finally by the run-length data after supplementing completely and without missing run-length data integration, to use in next step.
3 information table of stroke after the supplement of table 3
| Bayonet number | License plate number | Spend the vehicle time | Trip number |
| 343 | Anhui CXXXXX | 2017-06-0121:35:20 | 3 |
| 344 | Anhui CXXXXX | 2017-06-0121:36:35 | 3 |
| 345 | Anhui CXXXXX | 2017-06-0121:37:35 | 3 |
| 024 | Anhui CXXXXX | 2017-06-0121:39:27 | 3 |
| 187 | Anhui CXXXXX | 2017-06-0121:42:10 | 3 |
Step 3 extracts road traffic state information
The data for having missing supplement is complete rear together with the Data Integration of no missing, can be to the flow in section, speed
Degree and density are calculated.Calculation method is as follows:
(1), one day time was divided into 144 periods for the period with 10 minutes, by the temporal information in every data
For judgment basis, the data in each 10 minute period are traversed, extract the bayonet number of every data, license plate number, mistake
The information such as vehicle time, vehicle is every will to be generated one by a bayonet and crosses vehicle record, thus while calculating flow need to only count it is each
The item number continuously across certain two adjacent bayonet data in 10 minute period, the stream in section as where the two adjacent bayonets
Amount.If certain vehicle passes through first bayonet in certain section, the record time in previous 10 minute period, blocks by second
When mouth, the time is recorded in next 10 minute period, the then flow being included into previous 10 minute period.It counts in this way
It calculates, the flow information in you can get it each section each 10 minute period finally numbers its section, the period, and flow is stored in number
According to each section in library, can be obtained in the flow of each period.
(2), section speed still was calculated for the period with 10 minutes, is numbered by the bayonet that stroke reads data, license plate number, mistake
The information such as vehicle time calculate the time difference per two adjacent datas and store in seconds, the last item of each stroke
The time difference of data is denoted as 0, then can obtain corresponding road section at it divided by its time difference with adjacent two datas corresponding road section length
A velocity amplitude in vehicle time in corresponding 10 minute period is crossed, then to the number of speed in 10 minute period of each of each section
According to the section speed averaged within 10 minute period.By velocity information according to corresponding road section and corresponding period deposit
In database, each section can be obtained in the speed of each period.This example chooses the section that 13 category of roads are not quite similar
Its intraday velocity profile is drawn, as shown in Figure 4.
(3), road-section average density was calculated for the period with 10 minutes, is successively removed using the link flow in each 10 minute period
It is the road-section average density in period thus with corresponding road average-speed.Section is numbered, the period, section density is stored in number
According to each section in library, can be obtained in the density of each period.
The above is the principle that concrete case of the invention is implemented and its used, if to this under conception of the invention
Invention is changed, but when its function is still the spirit covered beyond specification and attached drawing, still falls within protection scope of the present invention.
Claims (3)
1. the urban road traffic state information extracting method under a kind of incomplete bayonet data qualification, it is characterised in that including such as
Lower step:
Step 1, the pretreatment of incomplete data
1.1 vehicle travels divide
The pretreatment of data includes recording the bayonet data put, and rejecting abnormalities data from all in selection road network in database
And repeated data；This partial data is classified according to license plate number, and distributes and numbers to each car；In chronological order to each
The data of vehicle are arranged；Finally, dividing to vehicle travel, division methods are as follows:
(1) section transit time set T={ T is arranged by required average time according to section each in road network normally travel1,
T2..., TV, the maximum of T in setu(u ∈ V) is used as threshold value.
(2) in above-mentioned data according to time sequence, if every two adjacent data time differences of each car are greater than threshold value, recognize
There is stop between the two record points for vehicle, needs data from the separated of the two record points, so by the two
Record puts the former and its pervious data and is considered as stroke A, and the latter and its later record point are considered as stroke B, if in=stroke B still
The case where having the adjacent data time difference to be greater than threshold value, can then continue stroke division to stroke B；
(3) stroke of only one record is rejected, and to remaining stroke distribution number to record stroke dividing condition；
1.2 calculating section evaluation indexes
Each link flow of primary Calculation and speed, two evaluation indexes needed for being calculated as subsequent entropy assessment, specific calculating side
Method is as follows:
(1) one day time is divided into n period using t as the period, the data in each period is traversed, extract each item number
According to bayonet number k, license plate number m, cross the information such as vehicle time s, calculate all directions in each time cycle by each bayonet
Vehicle number, the flow information q in you can get it each section each perioddj, wherein d is section number, and j is j-th of time cycle；
(2) section speed v still is calculated by the period of tdj, bayonet number k, the license plate number m of data are read by stroke, spend the vehicle time
The information such as s calculate the time difference per adjacent two data: Δ s=si+1-si, then can divided by the time difference with corresponding road section length
Speed is obtained, calculation formula is as follows:
Wherein vdiBy the bayonet number k of the i-th data and one of the bayonet number k+1 of the i+1 data section d connected
Velocity amplitude, Δ s are the difference of the time of i+1 data and the time of i data, ddFor the length of section d；
Seeking the speed average in its each section to the data in each period, i.e. the section speed in the period, formula are as follows thus:
Wherein, vdjFor the speed average of the section d in j-th of time cycle, ∑ vdjFor the section d of j-th time cycle
All velocity amplitude vdiSum, h is v in j-th time cyclediNumber.By section number d, period j, road average-speed
vdjIt is stored in database, each section can be obtained in the speed of each period；
(3) when the flow or speed in certain section have missing in certain period, then close using the flow of this section adjacent time interval or speed
Like substitution.
Step 2, completion missing data
If if location information shown by the data of certain stroke could be successively present in each adjacent bayonet of road network, i.e. its rail
Breakpoint is not present in mark information, then this trip data are without missing, directly using extracting road traffic state information；If certain stroke
Location information shown by data cannot sequentially link in road network, i.e., there are breakpoints for its trace information, then this trip data have
Missing just can be used after then supplementing completely the data of each of which breakpoint；The data for traversing each stroke extract its location information,
And its track is judged with the presence or absence of breakpoint, there are the run-length datas of shortage of data to be supplemented for extraction；
2.1 calculate the position of missing point
Data in the presence of missing are calculated with the track of its lack part using the depth-first traversal of optimization, specific steps are such as
Under:
(1) all possible paths of the corresponding beginning and end in shortage of data part are found out using the method for depth-first traversal,
And all possible paths are screened for the first time, find out wherein shortest path and differ small with the bayonet number that shortest path is passed through
In all paths for being equal to 3, if the collection of the possible path of certain stroke lack part is combined into R={ r1, r2..., rn, wherein riTable
Show the i-th paths in the set in path.Wherein n is the sum of qualified possible path；
(2) select path length, path average speed, section quantity and path average flow rate are as evaluation index；Path length
The length in each section that degree is passed through for every possible path be L={ l with set expression1, l2..., ln}T, wherein li(i∈
N) length and i.e. l in each section that i-th possible path is passed through are indicatedi=∑ dd；Path average speed can energy circuit for every
The speed average of each section that diameter is passed through during that corresponding time period, is V={ v with set expression1, v2..., vn}T, wherein vi
(i ∈ n) indicates the average speed v in each section that i-th possible path is passed throughdjAverage value, i.e., Section quantity
It is C={ c with set expression by the quantity in the section that every possible path passes through1, c2..., cn}T, wherein ci(i ∈ n) is indicated
The quantity in the section that i-th possible path is passed through；Each section that path average flow rate is passed through by every possible path is right
The flow average value in the period is answered, is Q={ q with set expression1, q2..., qn}T, wherein qi(i ∈ n) indicates i-th possibility
The flow q in each section that path is passed throughdjAverage value, i.e.,It is carried out really with weight of the entropy assessment to each evaluation index
It is fixed, initial matrix is obtained first:
(3) road average-speed and link flow are high excellent index, road section length and section quantity in aforementioned four evaluation index
For low excellent index, high excellent index is converted for low excellent index using counting backward technique, the matrix after conversion are as follows:
(4) Y matrix is normalized, i.e., with the element y of each column vector in Y matrixijWith the vector all elements
The corresponding element for the matrix Z that the ratio of sum is obtained as normalization, the matrix after normalization are as follows:
(5) the entropy weight H (x of each evaluation index is determinedj), (j=1,2,3,4), specific formula are as follows:
Wherein k is adjustment factor,zijFor the standardized value of j-th of evaluation index of i-th of evaluation unit, i.e., in Z matrix
I-th row, the element of jth column；
(6) weighted value is converted by the entropy of evaluation index, the weight of each evaluation index, specific formula can be obtained are as follows:
Wherein, djFor the weight of the evaluation index of jth column, and 0≤dj≤ 1,M is the number of evaluation index, i.e. m=
4。
(7) weight of each index, is distinguished corresponding criterion by the entropy weight comprehensive evaluation value for determining each evaluation index
Value is summed after being multiplied, formula are as follows:
Wherein, UiFor the entropy weight comprehensive evaluation value of i-th possible path；The maximum path of entropy weight comprehensive evaluation value is chosen as number
According to the track of lack part.
2.2 calculate the time of missing point
Using the temporal information of shortage of data partial traces point at Lagrangian type polynomial interpolation calculating, then you can get it
Link flow, section speed, road-section average vehicle density, the specific steps of which are as follows:
(1) the previous bayonet record for setting track data lack part is put as O point, the latter bayonet of track data lack part
Record point is D point, and enabling the previous bayonet of O point record point if having data before O point is A point, if no data A before O point
Point etc. and O point；The distance for enabling O point to A point is x0, the distance of D point to A point is x1, each tracing point of shortage of data part to A point
The collection of distance be combined into X={ x1,x2,…,xd, wherein xuThe distance of A point is arrived for u-th point；The time point of O point and D point is turned
Timestamp is turned to, and is denoted as y respectively0, y1；
(2) time value that each shortage of data partial traces point is calculated using Lagrangian type interpolation polynomial, can be obtained each rail
Set P={ the p of the time value of mark point1,p2,…,pd, wherein puFor u-th point of time value, Lagrangian type interpolation polynomial
The specific formula of formula are as follows:
Wherein 1≤u≤d, and xu∈X；
(3) time format in initial data is converted by the time value in set P, and the bayonet of corresponding tracing point is compiled
Number, license plate number, the excessively information such as vehicle time are added in this vehicle travel data can be complete by this trip information supplement.It will supplement
Data after complete and without missing Data Integration, to use in next step.
Step 3 extracts road traffic state information
(1) one day time was divided into n period using t as the time cycle, the data in each period is traversed, extracted each
Bayonet number k, the license plate number m of data cross the information such as vehicle time s, calculate in each time cycle by each of each bayonet
The vehicle number in direction, the flow q in you can get it each section each perioddj, wherein d is section number, and j is j-th of time cycle.
By section number d, period j, link flow qdjIt is stored in database, each section can be obtained in the flow of each period.
(2) section speed v still is calculated by the period of tdj, bayonet number k, the license plate number m of data are read by stroke, spend the vehicle time
The information such as s calculate the time difference per adjacent two data: Δ s=si+1-si, then can divided by the time difference with corresponding road section length
Speed is obtained, calculation formula is as follows:
Wherein vdiBy the bayonet number k of the i-th data and one of the bayonet number k+1 of the i+1 data section d connected
Velocity amplitude, Δ s are the difference of the time of i+1 data and the time of i data, ddFor the length of section d.
Seeking the speed average in its each section to the data in each period, i.e. the section speed in the period, formula are as follows thus:
Wherein, vdjFor the speed average of the section d in j-th of time cycle, ∑ vdjFor the section d of j-th time cycle
All velocity amplitude vdiSum, h is v in j-th time cyclediNumber.By section number d, period j, road average-speed
vdjIt is stored in database, each section can be obtained in the speed of each period；
(3) road-section average density is calculated by the period of t, successively using the link flow in each period divided by corresponding road-section average
The road-section average density in this period, calculation formula can be obtained in speed are as follows:By section number d, period j, section is close
Spend kdjIt is stored in database, each section can be obtained in the density of each period.
2. the urban road traffic state information extraction side under a kind of incomplete bayonet data qualification according to claim 1
Method, which is characterized in that in 1.2 (3) of the step one, if the flow for the section period acquired or speed have missing,
The flow or speed approximate substitution that adjacent time interval can be used, if the front and back adjacent time interval of specially numerical value loss period has number
According to then with the average value of front and back adjacent time interval come the value of this loss period of approximate substitution；If with the presence of multiple continuous time numerical value
Missing, then centre is substituted with the average value of front and back adjacent time interval, and all there are the values of numerical value loss period.
3. the urban road traffic state information extraction side under a kind of incomplete bayonet data qualification according to claim 1
Method, it is characterised in that in the 2.1 of the step two, the depth-first traversal of optimization is using depth-first traversal and entropy assessment
In conjunction with optimal way, find possible miss path using depth-first traversal, the superiority and inferiority in path then judged with entropy assessment,
To obtain the result of depth-first traversal of the most possible track for lack part as optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714830.9A CN108961747B (en) | 2018-07-03 | 2018-07-03 | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810714830.9A CN108961747B (en) | 2018-07-03 | 2018-07-03 | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108961747A true CN108961747A (en) | 2018-12-07 |
| CN108961747B CN108961747B (en) | 2019-11-05 |
Family
ID=64485102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810714830.9A Expired - Fee Related CN108961747B (en) | 2018-07-03 | 2018-07-03 | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108961747B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615865A (en) * | 2019-01-10 | 2019-04-12 | 北京工业大学 | A method of based on the iterative estimation road section traffic volume flow of OD data increment |
| CN110276950A (en) * | 2019-06-24 | 2019-09-24 | 华南理工大学 | A kind of urban transportation Trip chain reconstructing method based on bayonet video data |
| CN110599765A (en) * | 2019-08-16 | 2019-12-20 | 华南理工大学 | Road passenger and cargo transportation volume index statistical method based on multi-source data fusion |
| CN110634289A (en) * | 2019-09-04 | 2019-12-31 | 南京洛普股份有限公司 | Urban road traffic optimal path online planning method based on electric police data |
| CN110851755A (en) * | 2019-09-29 | 2020-02-28 | 口碑(上海)信息技术有限公司 | Method and device for acquiring delivery path information and electronic equipment |
| CN111047860A (en) * | 2019-12-02 | 2020-04-21 | 安徽百诚慧通科技有限公司 | Vehicle running track extraction method |
| CN111126687A (en) * | 2019-12-19 | 2020-05-08 | 银江股份有限公司 | Single-point off-line optimization system and method for traffic signals |
| CN111325993A (en) * | 2019-04-24 | 2020-06-23 | 北京嘀嘀无限科技发展有限公司 | Traffic speed determination method and device, electronic equipment and computer storage medium |
| CN111477015A (en) * | 2019-01-22 | 2020-07-31 | 上海宝康电子控制工程有限公司 | Method, device and storage medium for realizing intersection vehicle space-time distribution display control |
| CN112863174A (en) * | 2020-12-31 | 2021-05-28 | 华为技术有限公司 | Method and device for acquiring traffic flow information and computer equipment |
| CN113140114A (en) * | 2021-03-09 | 2021-07-20 | 中山大学 | Vehicle travel path reconstruction method based on travel time estimation |
| CN113255088A (en) * | 2021-05-21 | 2021-08-13 | 上海天壤智能科技有限公司 | Data completion method and system for bayonet vehicle-passing record |
| CN113763696A (en) * | 2020-06-01 | 2021-12-07 | 杭州海康威视数字技术股份有限公司 | Vehicle path reconstruction method and device, electronic equipment and storage medium |
| CN114999162A (en) * | 2022-08-02 | 2022-09-02 | 北京交研智慧科技有限公司 | Road traffic flow obtaining method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096756A (en) * | 2016-05-31 | 2016-11-09 | 武汉大学 | A kind of urban road network dynamic realtime Multiple Intersections routing resource |
| US9633560B1 (en) * | 2016-03-30 | 2017-04-25 | Jason Hao Gao | Traffic prediction and control system for vehicle traffic flows at traffic intersections |
| CN106997669A (en) * | 2017-05-31 | 2017-08-01 | 青岛大学 | A kind of method of the judgement traffic congestion origin cause of formation of feature based importance |
| CN107230350A (en) * | 2017-06-23 | 2017-10-03 | 东南大学 | A kind of urban transportation amount acquisition methods based on bayonet socket Yu mobile phone flow call bill data |
| CN107403551A (en) * | 2017-08-04 | 2017-11-28 | 广州市交通规划研究院 | A kind of quick identification of access connection traffic flow detection data and data reconstruction method |
-
2018
- 2018-07-03 CN CN201810714830.9A patent/CN108961747B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9633560B1 (en) * | 2016-03-30 | 2017-04-25 | Jason Hao Gao | Traffic prediction and control system for vehicle traffic flows at traffic intersections |
| CN106096756A (en) * | 2016-05-31 | 2016-11-09 | 武汉大学 | A kind of urban road network dynamic realtime Multiple Intersections routing resource |
| CN106997669A (en) * | 2017-05-31 | 2017-08-01 | 青岛大学 | A kind of method of the judgement traffic congestion origin cause of formation of feature based importance |
| CN107230350A (en) * | 2017-06-23 | 2017-10-03 | 东南大学 | A kind of urban transportation amount acquisition methods based on bayonet socket Yu mobile phone flow call bill data |
| CN107403551A (en) * | 2017-08-04 | 2017-11-28 | 广州市交通规划研究院 | A kind of quick identification of access connection traffic flow detection data and data reconstruction method |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615865A (en) * | 2019-01-10 | 2019-04-12 | 北京工业大学 | A method of based on the iterative estimation road section traffic volume flow of OD data increment |
| CN111477015A (en) * | 2019-01-22 | 2020-07-31 | 上海宝康电子控制工程有限公司 | Method, device and storage medium for realizing intersection vehicle space-time distribution display control |
| CN111325993A (en) * | 2019-04-24 | 2020-06-23 | 北京嘀嘀无限科技发展有限公司 | Traffic speed determination method and device, electronic equipment and computer storage medium |
| CN111325993B (en) * | 2019-04-24 | 2021-02-19 | 北京嘀嘀无限科技发展有限公司 | Traffic speed determination method and device, electronic equipment and computer storage medium |
| CN110276950A (en) * | 2019-06-24 | 2019-09-24 | 华南理工大学 | A kind of urban transportation Trip chain reconstructing method based on bayonet video data |
| CN110599765A (en) * | 2019-08-16 | 2019-12-20 | 华南理工大学 | Road passenger and cargo transportation volume index statistical method based on multi-source data fusion |
| CN110634289A (en) * | 2019-09-04 | 2019-12-31 | 南京洛普股份有限公司 | Urban road traffic optimal path online planning method based on electric police data |
| CN110851755A (en) * | 2019-09-29 | 2020-02-28 | 口碑(上海)信息技术有限公司 | Method and device for acquiring delivery path information and electronic equipment |
| CN111047860A (en) * | 2019-12-02 | 2020-04-21 | 安徽百诚慧通科技有限公司 | Vehicle running track extraction method |
| CN111126687A (en) * | 2019-12-19 | 2020-05-08 | 银江股份有限公司 | Single-point off-line optimization system and method for traffic signals |
| CN111126687B (en) * | 2019-12-19 | 2023-05-30 | 银江技术股份有限公司 | Single-point offline optimization system and method for traffic signals |
| CN113763696A (en) * | 2020-06-01 | 2021-12-07 | 杭州海康威视数字技术股份有限公司 | Vehicle path reconstruction method and device, electronic equipment and storage medium |
| CN112863174A (en) * | 2020-12-31 | 2021-05-28 | 华为技术有限公司 | Method and device for acquiring traffic flow information and computer equipment |
| CN112863174B (en) * | 2020-12-31 | 2022-05-17 | 华为技术有限公司 | Method and device for acquiring traffic flow information and computer equipment |
| CN113140114A (en) * | 2021-03-09 | 2021-07-20 | 中山大学 | Vehicle travel path reconstruction method based on travel time estimation |
| CN113140114B (en) * | 2021-03-09 | 2022-07-29 | 中山大学 | Vehicle travel path reconstruction method based on travel time estimation |
| CN113255088A (en) * | 2021-05-21 | 2021-08-13 | 上海天壤智能科技有限公司 | Data completion method and system for bayonet vehicle-passing record |
| CN114999162A (en) * | 2022-08-02 | 2022-09-02 | 北京交研智慧科技有限公司 | Road traffic flow obtaining method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108961747B (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108961747B (en) | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification | |
| CN108346292B (en) | Urban expressway real-time traffic index calculation method based on checkpoint data | |
| CN105869405B (en) | Urban road traffic congestion index calculation method based on bayonet socket data | |
| CN105719489B (en) | A kind of fake-licensed car detection method that probability is flowed to based on bayonet vehicle | |
| CN104200669B (en) | Fake-licensed car recognition method and system based on Hadoop | |
| CN102081846B (en) | Expressway charge data track matching based traffic state recognition method | |
| CN104021671B (en) | The determination methods of the road real-time road that a kind of svm combines with fuzzy Judgment | |
| CN105355049B (en) | A kind of highway evaluation of running status method based on macroscopical parent map | |
| CN104732765B (en) | Urban road saturation degree method of real-time based on bayonet socket data | |
| CN105740904B (en) | A kind of trip based on DBSCAN clustering algorithm and activity pattern recognition methods | |
| CN110162588A (en) | A kind of track fusion method of multidimensional related information | |
| CN102521965A (en) | Effect evaluation method of traffic demand management measures based on identification data of license plates | |
| CN106446208A (en) | Method for identifying traveling mode of smart phone by considering integrating degree of road network | |
| CN106022296A (en) | Fake plate vehicle detection method based on vehicle hot spot area probability aggregation | |
| CN112734219B (en) | Vehicle transportation running behavior analysis method and system | |
| CN103760901A (en) | Rail transit fault identification method based on association rule classifier | |
| CN105513362B (en) | A kind of bus platform adjacent area bus running state evaluation verification method | |
| CN110379169A (en) | Area to be transferred lane saturation headway calculation method based on video number plate equipment | |
| CN106898142A (en) | A kind of path forms time reliability degree calculation method of consideration section correlation | |
| CN114596700B (en) | Real-time traffic estimation method for expressway section based on portal data | |
| CN106327864A (en) | Traffic flow estimation method based on network charging data of highway | |
| CN102700576A (en) | Passenger flow monitoring method of urban rail traffic network | |
| CN109977108A (en) | A kind of a variety of track collision analysis methods in Behavior-based control track library | |
| CN106530704A (en) | Floating car aggregation detection method based on multivariate data fusion | |
| CN109684373A (en) | Emphasis party based on trip and call bill data analysis has found method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191105 Termination date: 20210703 |